CORTEXA
← Browse
semantic_scholare-Journal of Nondestructive Testing2026-08-01Cited by 0

BRDF-Based Photometric Stereo with AI Anomaly Detection for Fine Defect Inspection on Painted Electronic Buttons

Taesan Mo, Penghua Zhang, Seohyeon Jeong, Yeseul Kong, Gyuhae Park

TL;DR: A BRDF-based Photometric Stereo approach that accounts for complex reflectance characteristics when capturing fine geometric features of painted button surfaces, effectively enhancing the detectability of micro-defects that are visually indistinct in painted automotive components.

Ensuring the visual appearance quality of automotive interior buttons requires reliable inspection of painted surfaces. However, powder-coated finishes present complex reflectance behaviors, including directional glare and irregular highlight patterns, which often mask or resemble subtle defect features. To address this limitation, we explore a BRDF-based Photometric Stereo (PS) approach that accounts for complex reflectance characteristics when capturing fine geometric features of painted button surfaces. Leveraging BRDF-based modeling and multi-directional illumination, the PS method derives pixel-wise surface normals that are more robust to specular highlights and better represent true surface geometry. These surface normal maps are subsequently utilized as input to a deep learning model for detecting defective and anomalous surface regions. When integrated with AI-based anomaly detection, PS-derived geometric representations contributed to more reliable identification of fine surface irregularities, effectively enhancing the detectability of micro-defects that are visually indistinct in painted automotive components.

View free PDFSource page

Related papers

semantic_scholare-Journal of Nondestructive Testing2026-08-01

Reducing Experimental Data Requirements in CNN-based damage detection through Transfer Learning

Finja Rentzsch holm, Tobias Schalm, Jorge Luis Jiménez Aparicio, K. Schröder

TL;DR: This study demonstrates that transfer learning enables efficient adaptation to real-world conditions, offering a cost-effective and scalable solution for data-driven SHM.

While neural networks represent a promising approach for evaluating sensor data to assess damage presence, location and severity, large amounts of data are required for training. However, the generation of experimental data is both labor-intensive and costly. Transfer learning is…

View free PDFSource page
semantic_scholare-Journal of Nondestructive Testing2026-08-01

An Integrated Hybrid Framework for Crack Detection on Pressed Panels with Baseline-Driven False-Positive Suppression

Geon Park, Yeseul Kong, Penghua Zhang, Gyuhae Park

TL;DR: A baseline-panel–driven correction map that utilizes prior information extracted from healthy panels is introduced that enhances the stability and accuracy of crack detection, enabling more reliable inspection under the challenging lighting conditions of real automotive press lines.

Crack detection on pressed panels is essential for maintaining quality in automotive manufacturing. However, achieving stable inspection is challenging due to strong reflections on metallic surfaces, geometric curvature, and varying illumination conditions. To address these issue…

View free PDFSource page
semantic_scholare-Journal of Nondestructive Testing2026-08-01

Data-Driven Crack Detection Framework for Full-Scale Fatigue Tests Based on Principal Component Analysis

Y. Ofir, Efrat Pinhas, Y. Freed, Yael Buimovich, Gil Noivirt, Orly Dolev, et al.

Full-scale fatigue testing is a standard and essential procedure in the development of new air vehicles. In this process, a full-scale aircraft is used as a test article and subjected to fatigue loads representing the loads expected during its life. Dozens of hydraulic loading ja…

View free PDFSource page
semantic_scholare-Journal of Nondestructive Testing2026-08-01

On Heterogenous Bridge Monitoring Across Various Structural Changes by Hybridized Unsupervised Learning

Yu Wu, Amirhossein Haydarzadeh, Alireza Entezami, Hassan Sarmadi

Ensuring the long-term integrity and health of bridge structures under diverse structural, environmental, and operational conditions remains a persistent challenge within the structural health monitoring (SHM) community. Although machine learning–aided unsupervised anomaly detect…

View free PDFSource page
semantic_scholare-Journal of Nondestructive Testing2026-08-01

AI‑Powered Real-Time Structural Health Monitoring Using Crack Detection, Vegetation Segmentation, and Depth Analysis

Rijja H, Rohith Varshighan S, S. Veeramachaneni, Sumedha Maharana

TL;DR: An AI-driven system that can provide comprehensive structural health diagnostics from a single input structural image, using six parallel computer-vision pipelines with experimentally validated real-time inference performance, forms a strong base toward automated, scalable, and data-driven structural health monitoring.

Context / Content: Civil infrastructure and heritage structures deteriorate with time due to environmental exposure, material aging, moisture ingress, pollution, and biological growth. Traditional inspection relies heavily on manual assessment, which is slow, risky, and subjectiv…

View free PDFSource page
semantic_scholare-Journal of Nondestructive Testing2026-08-01

Edge/Cloud hybrid architecture for time-domain SHM transfer learning

Ivan Arakistain, S. Mitoulis, S. Argyroudis, Konstantinos Banitsas, Jose Carlos Jimenez, Eric López villarragut, et al.

TL;DR: This study provides a validated pathway toward scalable, real-time, and feature-free SHM systems for deployment in operational bridge networks, supporting continuous monitoring, early damage detection, and maintenance decision-making in the future.

Current Structural Health Monitoring (SHM) systems remain constrained by their reliance on handcrafted feature extraction and centralized cloud processing, limiting their real-time performance, scalability, and deployment on resource-constrained infrastructure. This study seeks t…

View free PDFSource page